tech-divergence

tech-divergence is a skill for Claude Code, Codex from WellApp-ai/Well. It costs 19 tokens per session (1,360 once invoked), scanned A, original, MIT.

A decision-making skill that compares technical implementation options with an eight-part scoring matrix. High-risk choices are sent to a human review step called Gate 4.

In plain words
What is it for?
Use it during technical planning to compare architectures or implementation patterns, find decisions that need human approval, and proceed automatically with lower-risk choices.
Why use it?
Teams can choose an architecture too quickly when several approaches seem valid. The matrix exposes risks involving patterns, scope, data, dependencies, APIs, reversibility, security, and performance.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/wellapp-ai/well/tech-divergence
Any agent
npx skills add WellApp-ai/Well --skill tech-divergence
Clone the repo
git clone --depth 1 https://github.com/WellApp-ai/Well

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for tech-divergence

README.md
[![agentmods](https://agentmods.dev/badge/skills/wellapp-ai/well/tech-divergence.svg)](https://agentmods.dev/skills/wellapp-ai/well/tech-divergence)
Your own site
<a href="https://agentmods.dev/skills/wellapp-ai/well/tech-divergence"><img src="https://agentmods.dev/badge/skills/wellapp-ai/well/tech-divergence.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.01360
Opus 5 $0.00010 $0.00680
Sonnet 5 $0.00004 $0.00272
Haiku 4.5 $0.00002 $0.00136

Measured 5d ago against content hash 65c11451a1a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

tech-divergence scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

cursor-rules/skills/tech-divergence/SKILL.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Divergence Skill

Evaluate technical implementation options using an 8-dimension scoring matrix. Low scores auto-proceed; high scores (>= 4) trigger Gate 4 for human decision.

When to Use

  • During Plan Mode Phase 2 (Technical Diverge)
  • Before committing to a specific architecture or pattern
  • When multiple valid implementation approaches exist

Scoring Matrix (8 Dimensions)

Each dimension scores 0 (auto-proceed) or 1 (adds to checkpoint score):

Dimension 0 (Low Risk) 1 (Checkpoint)
Pattern Exists in codebase New pattern required
Scope Single domain Cross-domain impact
Data Model Add field to existing New entity/table
Dependencies Use existing libs New dependency
API Surface Internal only Public/breaking change
Reversibility Easy to undo Requires migration
Security Non-sensitive data Auth/permissions
Performance Simple CRUD Cache/queue/optimization

Phase 1: Gather Context

1.1 Query Pattern Library (Notion)

Check if similar patterns exist:

API-query-database:
  database_id: "[PATTERN_LIBRARY_DB_ID]"
  filter:
    property: "Domain"
    select:
      equals: "[current domain]"

1.2 Search Codebase

SemanticSearch: "How is [similar feature] implemented?"
Grep: "[pattern name]" in relevant directories

1.3 Query Context7 (External Libraries)

If new libraries are being considered:

Context7 MCP:
1. resolve-library-id: libraryName = "[library]"
2. get-library-docs: topic = "best practices", mode = "info"

Phase 2: Score Each Dimension

For each of the 8 dimensions, evaluate and score:

## Technical Divergence Score

| Dimension | Score | Rationale |
|-----------|-------|-----------|
| Pattern | 0/1 | [Exists/New] |
| Scope | 0/1 | [Single/Cross-domain] |
| Data Model | 0/1 | [Field/Entity] |
| Dependencies | 0/1 | [Existing/New] |
| API Surface | 0/1 | [Internal/Public] |
| Reversibility | 0/1 | [Easy/Migration] |
| Security | 0/1 | [Non-sensitive/Auth] |
| Performance | 0/1 | [CRUD/Optimization] |
| **TOTAL** | [0-8] | |

Read the full file on GitHub · 207 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 207 lines · 19 tokens per session scan A 65c11451a1a4

Subscribe to this mod's changes

tech-divergence is a skill published in the GitHub repository WellApp-ai/Well (340 stars, last pushed 29d ago), licensed MIT. It adds 19 tokens to every session and 1,360 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

auto-reader-ocr

Extract text from images/PDFs (Arabic-first, manga-aware Japanese, 13+ languages auto-detected), translate between 100+ languages, and pull structured fields from invoices/receipts/IDs via the Auto-Reader OCR API. Use when the user shares a document image or PDF to read, translate, or extract data from — or asks for…

Samqra/auto-reader-ocr · 101 tokens

ccxt-rust

CCXT cryptocurrency exchange library for Rust developers. Covers both REST API (standard) and WebSocket API (real-time). Helps install CCXT, connect to exchanges, fetch market data, place orders, stream live tickers/orderbooks, handle authentication, and manage errors in Rust projects. Use when working with crypto…

ccxt/ccxt · 96 tokens

nextjs-pages-router

Set up tRPC in Next.js Pages Router with createNextApiHandler, createTRPCNext, withTRPC HOC, SSR via ssr option and ssrPrepass, SSG via createServerSideHelpers with getStaticProps, and server-side helpers for getServerSideProps prefetching.

trpc/trpc · 67 tokens

non-json-content-types

Handle FormData, file uploads, Blob, Uint8Array, and ReadableStream inputs in tRPC mutations. Use octetInputParser from @trpc/server/http for binary data. Route non-JSON requests with splitLink and isNonJsonSerializable() from @trpc/client. FormData and binary inputs only work with mutations (POST).

trpc/trpc · 75 tokens

scalar-docs

Skill for writing and updating scalar.config.json — Scalar Docs configuration reference for users and LLMs.

scalar/scalar · 24 tokens

horse-integration-tests

Guide for writing automated integration tests for Horse endpoints using DUnit/DUnitX and THTTPClient.

HashLoad/horse · 25 tokens